vacancy/SceneGraphParser

A python toolkit for parsing captions (in natural language) into scene graphs (as symbolic representations).

43
/ 100
Emerging

When you have a natural language sentence describing a scene, this tool helps you automatically break it down into a structured 'scene graph'. It takes your text descriptions as input and outputs a clear list of objects (like 'woman' or 'piano') and the relationships between them (like 'woman playing piano'). This is useful for researchers and developers working on projects that need to understand visual content from text.

592 stars. No commits in the last 6 months.

Use this if you need to extract structured data about objects and their interactions from descriptive sentences, especially for tasks involving image or video analysis.

Not ideal if you're looking for a tool to analyze complex sentiment, generate text, or perform general-purpose natural language understanding beyond scene description.

natural-language-processing computer-vision scene-understanding information-extraction visual-question-answering
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

592

Forks

55

Language

Python

License

MIT

Category

image-captioning

Last pushed

Jan 23, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/vacancy/SceneGraphParser"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.